Fixing bug setting index when parsing Google Vertex AI results

[ymao1]

For the Google Vertex AI rerank API, for an infer request with the following example inputs:

{
  "input": [
    "A canvas stretched across the day,\nWhere sunlight learns to dance and play.\nBlue, a hue of scattered light,\nA gentle whisper, soft and bright.",
    "The sky appears blue due to a phenomenon called Rayleigh scattering. Sunlight is comprised of all the colors of the rainbow. Blue light has shorter wavelengths than other colors, and is thus scattered more easily."
  ]
}

We create a request that looks like this, following the API specs

"records": [
   {
       "id": "1",
       "content": "A canvas stretched across the day,\nWhere sunlight learns to dance and play.\nBlue, a hue of scattered light,\nA gentle whisper, soft and bright."
   },
   {
       "id": "2",
       "content": "The sky appears blue due to a phenomenon called Rayleigh scattering. Sunlight is comprised of all the colors of the rainbow. Blue light has shorter wavelengths than other colors, and is thus scattered more easily."
   }
]

Note that for the ID, we use the index of the entry in the input array

elasticsearch/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/request/googlevertexai/GoogleVertexAiRerankRequestEntity.java

Lines 47 to 53 in 6d963d3

	for (int recordId = 0; recordId < inputs.size(); recordId++) {
	builder.startObject();
	{
	builder.field(ID_FIELD, String.valueOf(recordId));
	builder.field(CONTENT_FIELD, inputs.get(recordId));
	}

The API response is an array of records, sorted in descending order by score, for example

{
    "records": [
        {
            "id": "2",
            "score": 0.98,
            "content": "The sky appears blue due to a phenomenon called Rayleigh scattering. Sunlight is comprised of all the colors of the rainbow. Blue light has shorter wavelengths than other colors, and is thus scattered more easily."
        },
        {
            "id": "1",
            "score": 0.64,
            "content": "A canvas stretched across the day,\nWhere sunlight learns to dance and play.\nBlue, a hue of scattered light,\nA gentle whisper, soft and bright."
        }
    ]
}

In our response parser, we were not using the record ID (index of the entry in the input array) as the index into our result array, resulting in results where the score did not match up to the entry in the input array.

[elasticsearchmachine]

Pinging @elastic/ml-core (Team:ML)

[elasticsearchmachine]

Hi @ymao1, I've created a changelog YAML for you.

[jonathan-buttner]

How about we catch the NumberFormatException that could be thrown by parseInt and provide a more friendly message about what went wrong?

Maybe add a test for an invalid integer too.

[ymao1]

Updated in 68e2721

[jonathan-buttner]

Thanks for the change!

[elasticsearchmachine]

💚 Backport successful

Status	Branch	Result
✅	8.x